Odysseus is a self-hosted AI workspace with chat, deep research, memory, skills, calendar, notes, and document tools.
Launch in your Sealos workspace.
Start with the resources defined by the Odysseus template. Review CPU, memory, persistent storage, and network allocations for every service in Canvas. Capacity needs depend on your data and workload; monitor usage as they grow.
Template configuration and setupUse the application URL or connection details shown in Canvas. Follow the deployment guide for first-time account setup or client configuration, and keep generated credentials available for that step.
Sealos monthly plans include compute, memory, storage, and traffic. Size your plan for all deployed services. Software licenses and external AI or API services may have separate terms and charges. Confirm the applicable plan and optional charges in Cost Center.
Compare Sealos resource plansFor current cloud charges, refer to Sealos plan pricing. Upstream documentation may reference earlier billing models.
Odysseus is a self-hosted AI workspace for chat, autonomous agents, tools, model serving, email, research, notes, and memory. This template deploys the official Odysseus 1.0.2 runtime bundle with Chroma vector memory, SearXNG search, ntfy notifications, persistent storage, and public HTTPS access on Sealos Cloud.
Odysseus runs as an authenticated web application backed by local SQLite data, file storage, Chroma, SearXNG, and ntfy. The main Odysseus service exposes the web UI and API on port 7000, while Chroma, SearXNG, and ntfy stay on the internal Sealos cluster network.
The template provisions four StatefulSets: the Odysseus application, Chroma for vector memory, SearXNG for metasearch, and ntfy for notifications. Persistent volumes store Odysseus data, logs, SSH state, Hugging Face cache, local model-serving files, Chroma data, SearXNG cache, and ntfy cache.
Odysseus uses SQLite plus in-process pollers and scheduled tasks. Keep the Odysseus StatefulSet at one replica so those writers share one database and one task scheduler.
The first administrator account is created from the deployment form values. On a fresh deployment, admin_user maps to ODYSSEUS_ADMIN_USER and admin_password maps to ODYSSEUS_ADMIN_PASSWORD.
The Sealos template includes the Odysseus application container, Chroma vector database, SearXNG search service, ntfy notification service, persistent storage, and an HTTPS ingress.
Architecture Components:
Configuration:
admin_user: Initial administrator username for a fresh Odysseus data volume.admin_password: Initial administrator password for a fresh Odysseus data volume.openai_api_key: Optional OpenAI API key for cloud model access.ALLOWED_ORIGINS: Set automatically to the Sealos public URL.SECURE_COOKIES: Enabled for the Sealos HTTPS endpoint.License Information:
Odysseus is licensed under AGPL-3.0-or-later. This Sealos template follows the same upstream license terms for the application it deploys.
Sealos is an AI-assisted Cloud Operating System built on Kubernetes that unifies application deployment, persistent storage, networking, and operations. Deploying Odysseus on Sealos gives you:
admin_user: Initial administrator username, such as admin.admin_password: Initial administrator password.openai_api_key: Optional OpenAI API key.admin_user and admin_password.After login, configure model providers, local endpoints, SearXNG-backed research, memory settings, tools, email, calendar, and user permissions from the Odysseus UI. For infrastructure changes, use the Sealos Canvas AI dialog or click the relevant StatefulSet, Service, Ingress, or storage resource cards.
The initial admin credentials are used when Odysseus creates /app/data/auth.json on an empty data volume. Existing deployments keep the accounts stored in the persistent data volume.
To scale or tune Odysseus:
/app/data/auth.json on the persistent data volume.This Sealos template is provided under the upstream repository license. Odysseus itself is licensed under AGPL-3.0-or-later.
A shorter path from an app you want to an app you can run. Sealos brings deployment and ongoing operations into one place.
Start with a ready-made template. Review its configuration and launch from the Sealos console.
Run on managed infrastructure with built-in workload scheduling and recovery.
Give your application a public HTTPS endpoint with certificates managed for you.
Keep application data on persistent volumes across container restarts.
Adjust CPU, memory, and replicas from the console as your workload changes.
Sealos provisions the resources defined by your template and brings them together in your workspace.
Container workloads with configurable CPU, memory, and replicas.
An address for your app, with managed TLS certificates.
A database provisioned alongside your app when the template calls for one.
Storage for the files and data your application needs to keep.
Application settings and secrets configured in one place.
Inspect container logs and resource usage from the console.
Resources and their configuration vary by template. Review the deployment form for this app’s exact setup.
Explore more production-ready templates.
Build production-ready ai templates with Sealos.
Open Design is a local-first, open-source AI design workspace for generating prototypes, decks, images, videos, and design-system-driven artifacts.
Build production-ready ai templates with Sealos.
Host OpenClaw's AI agent gateway on Sealos with a browser control panel, token authentication, and persistent storage for configuration and workspaces.
Build production-ready ai templates with Sealos.
Open-source AI model gateway compatible with the OpenAI API, with multi-provider routing, quota management, channel orchestration, and an admin dashboard.